We present an incremental joint framework to simultaneously extract entity mentions and relations using structured perceptron with efficient beam-search. A segment-based decoder based on the idea of semi-Markov chain is adopted to the new framework as opposed to traditional token-based tagging. In addition, by virtue of the inexact search, we developed a number of new and effective global features as soft constraints to capture the interdependency among entity mentions and relations. Experiments on Automatic Content Extraction (ACE) 1 corpora demonstrate that our joint model significantly outperforms a strong pipelined baseline, which attains better performance than the best-reported end-to-end system.

The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating "silver-standard" annotations by transferring annotations from English to other languages through crosslingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from crosslingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data. All the data sets, resources and systems for 282 languages are made publicly available as a new benchmark 1 .

Most existing joint neural models for Information Extraction (IE) use local task-specific classifiers to predict labels for individual instances (e.g., trigger, relation) regardless of their interactions. For example, a VICTIM of a DIE event is likely to be a VICTIM of an AT-TACK event in the same sentence. In order to capture such cross-subtask and cross-instance inter-dependencies, we propose a joint neural framework, ONEIE, that aims to extract the globally optimal IE result as a graph from an input sentence. ONEIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations;(2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder. At the decoding stage, we incorporate global features to capture the cross-subtask and cross-instance interactions. Experiments show that adding global features improves the performance of our model and achieves new state-of-the-art on all subtasks. As ONEIE does not use any language-specific feature, we prove it can be easily applied to new languages or trained in a multilingual manner. Our code and models for English, Spanish and Chinese are publicly available for research purpose 1 . PER Erdogan PER Abdullah Gul End-Position resigned Elect won person personExample: Prime Minister Abdullah Gul resigned earlier Tuesday to make way for Erdogan, who won a parliamentary seat in by-elections Sunday.

Distant supervision has been widely used in current systems of fine-grained entity typing to automatically assign categories (entity types) to entity mentions. However, the types so obtained from knowledge bases are often incorrect for the entity mention's local context. This paper proposes a novel embedding method to separately model "clean" and "noisy" mentions, and incorporates the given type hierarchy to induce loss functions. We formulate a joint optimization problem to learn embeddings for mentions and typepaths, and develop an iterative algorithm to solve the problem. Experiments on three public datasets demonstrate the effectiveness and robustness of the proposed method, with an average 15% improvement in accuracy over the next best compared method 1 .

No abstract

Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment classification without using any labeled documents but learning from unlabeled data supervised by at most 3 words (1 in most cases) per class as the label name 1 .

Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of communication, and has become increasingly common in such sites. This new paradigm brings new challenges for natural language understanding, as the textual component tends to be shorter, more informal, and often is only understood if combined with the visual context. In this paper, we explore the task of name tagging in multimodal social media posts. We start by creating two new multimodal datasets: one based on Twitter posts 1 and the other based on Snapchat captions (exclusively submitted to public and crowdsourced stories). We then propose a novel model based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-theart baseline methods for this task. 2 * * This work was mostly done during the first author's internship at Snap Research. 1 The Twitter data and associated images presented in this paper were downloaded from https://archive.org/ details/twitterstream 2 We will make the annotations on Twitter data available for research purpose upon request.

Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees. In this paper, we further explore how to make full use of the combination of these dependency information. We first propose a new structure, termed augmented dependency path (ADP), which is composed of the shortest dependency path between two entities and the subtrees attached to the shortest path. To exploit the semantic representation behind the ADP structure, we develop dependency-based neural networks (DepNN): a recursive neural network designed to model the subtrees, and a convolutional neural network to capture the most important features on the shortest path. Experiments on the SemEval-2010 dataset show that our proposed method achieves state-of-art results.